Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3460 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5204. Min Range: -2.5204

Max Act: 2.5204. Min Act: -0.0000

Data Index: 1224159 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 2.5204. Min Range: -2.5204

Max Act: 2.1369. Min Act: -0.0000

Data Index: 124356 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 2.5204. Min Range: -2.5204

Max Act: 2.0084. Min Act: -0.0000

Data Index: 1355621 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 2.5204. Min Range: -2.5204

Max Act: 2.1282. Min Act: -0.0000

Data Index: 815719 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 2.5204. Min Range: -2.5204

Max Act: 1.9102. Min Act: -0.0000

Data Index: 496552 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 2.5204. Min Range: -2.5204

Max Act: 1.7920. Min Act: -0.0000

Data Index: 193192 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 2.5204. Min Range: -2.5204

Max Act: 1.7889. Min Act: -0.0000

Data Index: 226848 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 2.5204. Min Range: -2.5204

Max Act: 1.6657. Min Act: -0.0000

Data Index: 493960 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 2.5204. Min Range: -2.5204

Max Act: 1.6163. Min Act: -0.0000

Data Index: 126800 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 2.5204. Min Range: -2.5204

Max Act: 1.6157. Min Act: -0.0000

Data Index: 803707 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 2.5204. Min Range: -2.5204

Max Act: 1.5875. Min Act: -0.0000

Data Index: 516195 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 2.5204. Min Range: -2.5204

Max Act: 1.4622. Min Act: -0.0000

Data Index: 20726 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 2.5204. Min Range: -2.5204

Max Act: 1.5791. Min Act: -0.0000

Data Index: 1263659 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 2.5204. Min Range: -2.5204

Max Act: 1.5684. Min Act: -0.0000

Data Index: 619099 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 2.5204. Min Range: -2.5204

Max Act: 1.5490. Min Act: -0.0000

Data Index: 1015741 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 2.5204. Min Range: -2.5204

Max Act: 1.5371. Min Act: -0.0000

Data Index: 749677 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 2.5204. Min Range: -2.5204

Max Act: 1.6379. Min Act: -0.0000

Data Index: 97000 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 2.5204. Min Range: -2.5204

Max Act: 1.5256. Min Act: -0.0000

Data Index: 466622 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 2.5204. Min Range: -2.5204

Max Act: 1.6240. Min Act: -0.0000

Data Index: 574205 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 2.5204. Min Range: -2.5204

Max Act: 1.5816. Min Act: -0.0000

Data Index: 684263 (C4 (Web Text))

Max Activating Token Index: 353